Use RubyLLM with Respan for multi-model access and observability

Overview

RubyLLM is a Ruby gem that provides a unified interface for interacting with AI models. When configured with Respan, it enables logging, analytics, fallbacks, and access to 250+ models through a single API key.

Switch between OpenAI, Anthropic, Google, and other providers by changing the model parameter. The integration supports streaming responses and Rails compatibility via initializer configuration.

How it works

Add ruby_llm to your Gemfile and run bundle install. Configure RubyLLM to point openai_api_base to https://api.keywordsai.co/api/ and provide your Respan API key.

Make requests using standard RubyLLM syntax. All requests are automatically logged to the Respan platform for analytics. Streaming is supported via block syntax.

ruby

# config/initializers/ruby_llm.rb
RubyLLM.configure do |config|
  config.openai_api_base = "https://api.keywordsai.co/api/"
  config.openai_api_key = ENV["RESPAN_API_KEY"]
end

# Usage
chat = RubyLLM.chat(model: "gpt-4o-mini")
response = chat.ask("What is the meaning of life?")